powerpc/eeh: Defer printing stack trace

Currently we print a stack trace in the event handler to help with
debugging EEH issues. In the case of suprise hot-unplug this is unneeded,
so we want to prevent printing the stack trace unless we know it's due to
an actual device error. To accomplish this, we can save a stack trace at
the point of detection and only print it once the EEH recovery handler has
determined the freeze was due to an actual error.

Since the whole point of this is to prevent spurious EEH output we also
move a few prints out of the detection thread, or mark them as pr_debug
so anyone interested can get output from the eeh_check_dev_failure()
if they want.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190903101605.2890-6-oohall@gmail.com

1 files changed, 12 insertions, 14 deletions

diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c
index e36653e5f76b..1d55486adb0f 100644
--- a/arch/powerpc/kernel/eeh_event.c
+++ b/arch/powerpc/kernel/eeh_event.c
@@ -40,7 +40,6 @@ static int eeh_event_handler(void * dummy)
 {
 	unsigned long flags;
 	struct eeh_event *event;
-	struct eeh_pe *pe;
 
 	while (!kthread_should_stop()) {
 		if (wait_for_completion_interruptible(&eeh_eventlist_event))
@@ -59,19 +58,10 @@ static int eeh_event_handler(void * dummy)
 			continue;
 
 		/* We might have event without binding PE */
-		pe = event->pe;
-		if (pe) {
-			if (pe->type & EEH_PE_PHB)
-				pr_info("EEH: Detected error on PHB#%x\n",
-					 pe->phb->global_number);
-			else
-				pr_info("EEH: Detected PCI bus error on "
-					"PHB#%x-PE#%x\n",
-					pe->phb->global_number, pe->addr);
-			eeh_handle_normal_event(pe);
-		} else {
+		if (event->pe)
+			eeh_handle_normal_event(event->pe);
+		else
 			eeh_handle_special_event();
-		}
 
 		kfree(event);
 	}
@@ -126,8 +116,16 @@ int __eeh_send_failure_event(struct eeh_pe *pe)
 	 * This prevents the PE from being free()ed by a hotplug driver
 	 * while the PE is sitting in the event queue.
 	 */
-	if (pe)
+	if (pe) {
+		/*
+		 * Save the current stack trace so we can dump it from the
+		 * event handler thread.
+		 */
+		pe->trace_entries = stack_trace_save(pe->stack_trace,
+					 ARRAY_SIZE(pe->stack_trace), 0);
+
 		eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+	}
 
 	/* We may or may not be called in an interrupt context */
 	spin_lock_irqsave(&eeh_eventlist_lock, flags);